{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:19:38Z","timestamp":1781713178059,"version":"3.54.5"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2018,5,1]],"date-time":"2018-05-01T00:00:00Z","timestamp":1525132800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"European Union FP7 ERC Advanced","award":["VHIA (#340113)"],"award-info":[{"award-number":["VHIA (#340113)"]}]},{"name":"XEROX University Affairs Committee (UAC)","award":["2015-2017"],"award-info":[{"award-number":["2015-2017"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2018,5,1]]},"DOI":"10.1109\/tpami.2017.2648793","type":"journal-article","created":{"date-parts":[[2017,1,5]],"date-time":"2017-01-05T19:39:19Z","timestamp":1483645159000},"page":"1086-1099","source":"Crossref","is-referenced-by-count":86,"title":["Audio-Visual Speaker Diarization Based on Spatiotemporal Bayesian Fusion"],"prefix":"10.1109","volume":"40","author":[{"given":"Israel D.","family":"Gebru","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sileye","family":"Ba","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5232-024X","authenticated-orcid":false,"given":"Radu","family":"Horaud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177983"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459303"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2405475"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.96"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1007\/978-3-319-22482-4_17","article-title":"Audio-visual speech-turn\n detection and tracking","author":"gebru","year":"2015","journal-title":"Proc Int Conf Latent Variable Anal Signal Separat"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/53.665"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.159"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.05.005"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070507"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2522425"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.888095"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362413"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.906583"},{"key":"ref12","first-page":"813","article-title":"Audio-vision: Using audio-visual synchrony to locate sounds","author":"hershey","year":"2000","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref13","first-page":"772","article-title":"Learning joint statistical\n models for audio-visual fusion and segregation","author":"fisher iii","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881678"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2057198"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2377515"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1007\/978-3-540-68585-2_47","article-title":"The ICSI rt07s speaker diarization system","author":"wooters","year":"2008","journal-title":"Multimodal Technologies for Perception of Humans"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00048-X"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.817150"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2013.6659295"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-012-1080-6"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2444654"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.47"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-014-2274-x"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00074"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2463722"},{"key":"ref8","first-page":"28","article-title":"The ami meeting corpus: A pre-announcement","author":"carletta","year":"2005","journal-title":"Proc Workshop Machine Learning for Multimodal Interaction"},{"key":"ref7","first-page":"1","article-title":"Multimodal speaker clustering in full length movies","author":"kapsouras","year":"2016","journal-title":"Multimedia Tools Appl"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"2654","DOI":"10.21437\/Interspeech.2010-704","article-title":"Audio-visual synchronisation for speaker diarisation","author":"garau","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.274"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.872619"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806238"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"488","DOI":"10.1007\/3-540-45113-7_48","article-title":"Speaker\n localisation using audio-visual synchrony: An empirical study","author":"nock","year":"2003","journal-title":"Proc Int Conf Image Video Retrieval"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2009.2037387"},{"key":"ref42","first-page":"182","article-title":"Av16.\n 3: An audio-visual corpus for speaker localization and tracking","author":"lathoud","year":"2004","journal-title":"Machine Learning for Multimodal Interaction"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1322192.1322254"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471661"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366271"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.150"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2011.09.032"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"2170","DOI":"10.21437\/Interspeech.2012-579","article-title":"Diartk: An open source toolkit for research in multistream speaker diarization and its\n application to meetings recordings.","author":"vijayasenan","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2029711"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8329157\/07807334.pdf?arnumber=7807334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T07:50:24Z","timestamp":1643183424000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7807334\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,1]]},"references-count":45,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2017.2648793","relation":{},"ISSN":["0162-8828","2160-9292"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,5,1]]}}}